A neural network for fusing the MR information into PET images to improve spatial resolution

Author

Sase, Mikiya ; Kinoshita, Naoyuki ; Kosugi, Yukio

Author_Institution

Interdisciplinary Graduate Sch. of Sci. & Eng., Tokyo Inst. of Technol., Yokohama, Japan

Volume

3

fYear

1994

fDate

13-16 Nov 1994

Firstpage

908

Abstract

We propose a neural network architecture to fuse the anatomical information given by an MR image, into a PET image to reconstruct a reasonable activity distribution in the brain. In the network, convolutional parameters and the anatomical brain structure are expressed in pre-wired weights. When an observed PET image is given to the comparison side of the network, the activity profile of the activity layer is iteratively adjusted to constitute a reasonable model for the positron generating profile, using a modified network inversion technique

Keywords

biomedical NMR; brain; image reconstruction; image resolution; medical image processing; neural nets; positron emission tomography; MR image; PET images; activity profile; anatomical brain structure; anatomical information; brain activity distribution; convolutional parameters; image reconstruction; iterative adjustment; network inversion technique; neural network; positron generating profile; pre-wired weights; spatial resolution; Biological neural networks; Blood flow; Deconvolution; Fuses; Image reconstruction; Image resolution; Imaging phantoms; Neural networks; Positron emission tomography; Spatial resolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference

Conference_Location

Austin, TX

Print_ISBN

0-8186-6952-7

Type

conf

DOI

10.1109/ICIP.1994.413714

Filename

413714